MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Graph-structured tool retrieval for LLM agents — zero-dependency, ontology-aware hybrid search
pypi MIT -
@aidevkit/graphgithub.com/semihkayan/aidevkit-graphupdated this year
Codebase graph analysis for AI agents — AST + call graph + type graph + hybrid semantic search via MCP
npm Apache-2.0 -
claude-graphgithub.com/mohansagark/claude-graphupdated this year
Local-only knowledge graph of your codebase for Claude Code — Tree-sitter + SQLite + MCP, zero network calls ever
MIT ★ 1 -
claude-graphgithub.com/mohansagark/claude-graphupdated this year
Local knowledge graph for Claude Code — call graphs, impact radius, and code search via MCP, powered by Tree-sitter and SQLite. Supports Python, JS/TS, Go, Rust, Java, C#, Ruby, C/C++, Swift and more.
pypi MIT -
A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.
npm MIT ★ 11 -
A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.
npm MIT -
@codeweave/mcpgithub.com/semihkayan/codeweave-mcpupdated this year
Codebase graph analysis for AI agents — AST + call graph + type graph + hybrid semantic search via MCP
npm Apache-2.0 -
codemap-aiupdated this year
Call graph analyzer for understanding code impact and execution flows - built for Claude Code
npm MIT -
Personal pre-indexed code knowledge graph for Java, Ruby, TypeScript and JavaScript — a call graph plus nine string-binding plugins for the wiring a call graph structurally cannot see: MyBatis, Camel, SQS, Kafka, HTTP routes, Spring events, GraphQL, gRPC, Flyway. Runs entirely offline.
MIT ★ 1 -
A precise, local code graph for coding agents: who calls what, what breaks, which tests to run
NOASSERTION ★ 1 -
The call graph from your compiler or type checker, for humans and coding agents
MIT ★ 4 -
Code graph for AI agents: impact analysis and call tracing over MCP (Python, TypeScript). Local, deterministic, SQLite.
MIT ★ 2 -
Deterministic tree-sitter + SQLite/FTS5 code knowledge graph for coding agents and developers: symbols, calls and dependencies over a CLI, an MCP server and a local browser viewer. No AI/LLM inside; byte-stable output.
MIT ★ 22 -
Euthynos — deterministic repository intelligence for AI coding agents (MCP server): exact source spans, call graphs, clone detection, honest evidence boundaries.
npm Apache-2.0 -
Python package on PyPI (not a Rust crate): a code graph of routes, calls, data access and platform boundaries. pip install cg-code-graph
pypi MIT -
AST-based code navigation for AI agents: static analysis and call graphs instead of vector search. Includes an MCP server (cdd-mcp).
MIT -
Deterministic code map for AI coding agents: a tree-sitter symbol and call graph served over MCP and a CLI, with no embeddings, network or telemetry.
npm Apache-2.0 ★ 1 -
code-graphgithub.com/valarpirai/code-graphupdated this year
Pre-indexed code knowledge graph for Claude Code, Codex, OpenCode — fewer tokens, fewer tool calls, 100% local. Perfect for code exploration
MIT ★ 1 -
@1337xcode/cortexgithub.com/1337xcode/cortexupdated this year
Code intelligence MCP server. Indexes your repository into a confidence-aware call graph with SCIP ingestion, framework adapters, and evidence-fusion ranking for AI coding agents.
npm MIT -
See what your AI edits affect. Structural checks for AI code changes. Local call/import graphs and 28 MCP tools for impact, callers, and duplication. No LLM in the checks.
MIT -
See what your AI edits affect. Structural checks for AI code changes. Local call/import graphs and 28 MCP tools for impact, callers, and duplication. No LLM in the checks.
npm MIT -
LynxMCP: local MCP server for the code questions grep can't answer. Call graph and blast radius, hybrid semantic + lexical code search on ONNX Runtime, library docs and PDFs as sources. No cloud, no PyTorch.
Apache-2.0 ★ 11 -
orihimegithub.com/srinivasan-sundaresan95/orihimeupdated this year
Cross-repo code knowledge graph for Java/Kotlin/JS/TS — MCP server, taint analysis, call graph, OWASP reports. 95% fewer tokens than source-reading.
★ 2 -
Local code index for AI agents. Scans a repo with tree-sitter into one SQLite file — function inventory, call graph, module deps, control flow, impact analysis — then serves 32 MCP tools to Claude Code, Cursor and VS Code. No LLM calls, no upload, no telemetry. npm i -g codindex
MIT ★ 3 -
@hayasaka7/go-arch-xraygithub.com/hayasaka7/go-arch-xrayupdated this year
Model Context Protocol server for static analysis of Go codebases with shadow SQLite indexing, background sync, call graphs, import graphs, interface topology, struct lifecycle, endpoints, maintainability metrics, and repo-aware config.
npm MIT -
codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work
NOASSERTION ★ 4 -
Graph-Augmented Code Intelligence RAG engine pairing deterministic AST call graphs with dense vector search to boost direct-callee Recall@8 from 0.0% to 53.3% (+53.3 pp) under a 5.8ms p95 latency bound. Powered by a QLoRA fine-tuned Qwen2.5 adapter (70.02 CodeBLEU), quality verification harness, and production Model Context Protocol (MCP) server.
MIT -
Save 6-8× tokens on AI code reviews. Builds a structural call graph via Tree-sitter + MCP. Works with Claude, Kimi, Gemini, ChatGPT, Cursor, Windsurf — any AI assistant.
MIT ★ 2 -
轻量级代码智能 MCP:AST + 增量索引 + 调用图,无 embedding。Lightweight code intelligence MCP: AST, incremental index & call graph.
MIT -
CALMgithub.com/Eilodon/CALMactive
A live, graph-verified map of your codebase for AI coding agents — real call graphs, compiler-verified edges, and hard safety gates on the write path.
MIT ★ 17 -
kernava-mcpgithub.com/nordicnode/kernava-mcpupdated this year
Graph-backed coding intelligence MCP server in Rust. tree-sitter parsing (11 languages), SQLite-WAL + FTS5, in-RAM call graph, Louvain communities. 16 MCP tools over streamable HTTP.
NOASSERTION ★ 1 -
ctx — a queryable code graph for coding agents, across Rust, Python, TypeScript and Go. Call graphs, blast radius, breaking-change gates, port parity. One binary, no LSP, no index.
MIT ★ 3 -
codemunch-progithub.com/BigJai/codemunch-proupdated this year
Intelligent code indexing MCP server. 13 tools, 10 languages, hybrid search, call graphs, O(1) symbol retrieval.
MIT ★ 3 -
aptu-coder: MCP server for AST analysis, call graphs, and code structure (tree-sitter)
Apache-2.0 ★ 7 -
code-tracer-mcpgithub.com/ezulabs/code-tracer-mcpupdated this year
MCP server that traces call graphs, maps HTTP routes, and analyzes TypeScript/Next.js codebases.
-
codeweave-mcpgithub.com/semihkayan/codeweave-mcpupdated this year
MCP server that gives AI agents semantic search tool. Builds AST, call graphs, type graphs, and hybrid semantic search — so your agent queries structured indexes instead of dumping files into context. 7 languages. Zero config. One command setup.
npm Apache-2.0 ★ 4 -
callscopegithub.com/benwelker/callscopeupdated this year
A zero-dependency, local, interactive call-graph navigator for Python codebases. One script in, one self-contained HTML file out
MIT ★ 1 -
MCP server that gives AI coding agents an LSP call graph for one symbol: callers, callees, implementations, tests and impacted files in one call, instead of reading whole files.
npm GPL-3.0-or-later -
Lightweight code indexing and exploration powered by Lua, with multi-language symbol extraction, call graphs, and incremental updates.
npm BSD-2-Clause -
tokennukegithub.com/bigjai/tokennukeupdated this year
Intelligent code indexing MCP server. Tree-sitter AST extraction, hybrid search (FTS5 + vector), call graphs, 10 languages, incremental indexing. Save 99% of tokens.
pypi MIT -
MCP server: LSP call graph for AI coding agents. One symbol’s callers, callees, tests and impacted files in one call instead of reading whole files, saving tokens. Claude Code & Codex plugin.
GPL-3.0 -
Code map & call-graph MCP server for AI agents. Tree-sitter + SQLite index of PHP/Go/TS code with type-inference enrichment — semantic search, callers, implementations in milliseconds.
MIT ★ 2 -
Scan C/C++/Go/Python/Java/Rust/etc. codebases and generate directed call graphs with call ordering, conditions, conditional compilation paths, concurrency analysis, and confidence classification. Designed to give LLM agents global-to-local code understanding — first load a compact context pack, then drill into specific functions on demand.
MIT ★ 1 -
A token-efficient code map for AI coding agents: outline, call graph, "who calls this?" and impact analysis without reading whole files. PHP, TS/Vue, Rust, Swift, Python, Go. One binary, CLI + MCP.
MIT ★ 14 -
Local MCP server for read-only C# code navigation and .NET assembly inspection. Roslyn symbol search, call graphs, references, type hierarchies, and ILSpy decompilation for AI coding agents.
MIT -
Cut 95% wasted tokens, stop breaking changes with sub-2ms call-graphs, and ban AI code slop. Universal MCP toolkit for Cursor, Claude Code, Antigravity & Windsurf.
MIT ★ 4 -
Deterministic code map for AI coding agents: a tree-sitter symbol and call graph served over MCP and a CLI, with no embeddings, network or telemetry.
npm Apache-2.0 -
Local code intelligence and project memory for Codex and Claude Code. Explore TypeScript, JavaScript and Prisma through call graphs, model usage and source context. Project-scoped MCP server with a shared CLI.
MIT ★ 1 -
n24q02m-crgactive
Token-efficient code review knowledge graph: semantic search and call-graph resolution.
pypi Apache-2.0 -
mcpgithub.com/supermodeltools/mcpupdated this year
Save up to 40% on agent token costs with code graphs: call graphs, dependency graphs, dead code detection, and blast radius analysis.
MIT ★ 17 -
Cross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius, health grading, 8 facade tools, JSON envelopes, 100% local. Run miswire-audit on your repo.
MIT ★ 61 -
context-enginegithub.com/JaimeJunr/context-engineupdated this year
Drop-in token saver for Claude Code & MCP agents — auto-rewrite hooks + 10-tool MCP server + BM25/PageRank repo maps + call graphs in 7 languages + local RAG. Single Rust binary, 100% local, zero APIs.
Apache-2.0 ★ 2 -
Framework-aware code intelligence for LLM agents. Indexes Java, Python, TypeScript, Go, Scala into a verified call graph via tree-sitter + Rust. MCP server, Haiku sub-agent, and git hooks included. 68–95% agent token reduction.
MIT ★ 1 -
crggithub.com/n24q02m/crgactive
Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.
pypi Apache-2.0 ★ 76 -
Index any TypeScript/React repo (incl. monorepos) into a queryable code graph — npx CLI, HTTP/WS + MCP server, 3D viewer. who-renders, who-calls, blast-radius, cycles, dead-code. npm: code-graph-indexer
MIT ★ 2 -
A memory of the codebase your AI agent can't get from grep: a persistent call graph, semantic search, and per-symbol review learnings over any repo. Self-hosted MCP server — Go, tree-sitter, Apache AGE.
Apache-2.0 ★ 6 -
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
npm NOASSERTION ★ 515 -
Static code map generator (MAP.md + map.json) powered by tree-sitter — a Claude Code /map plugin and MCP server that gives coding agents call graphs, file outlines, and impacted-test lookups without spending tokens on parsing.
MIT ★ 6 -
5D Living Code Graph, 1-Call Subagent Context (chronos_explore), 4-Angle Review Audit, Surface Tracer, Universal Multi-Agent Synthesizer (Codex/Antigravity/Claude/OpenCode/Cursor) & Super-Mutant Gate (12 MCP Tools)
MIT ★ 2 -
LatentContext MCP Server: session-isolated memory, a knowledge graph, and a live code index with call graphs for MCP hosts
npm MIT